An egg production monitoring method, apparatus, device, medium, and product

Abstract

Embodiments of the present application disclose an egg production monitoring method, device, equipment, medium and product, and relate to the technical field of Internet of Things. The egg production monitoring method comprises: acquiring an RFID time sequence of a target bird in a current monitoring period, the RFID time sequence comprising monitoring values corresponding to monitoring time points in the current monitoring period, the monitoring value indicating whether an RFID tag set on the target bird is read by an RFID reader set in an egg production area at the corresponding monitoring time point; extracting multi-scale time sequence features from the RFID time sequence, inputting the multi-scale time sequence features into an egg production probability prediction model to predict an egg production probability, and obtaining a predicted egg production probability; wherein the egg production probability prediction model is trained based on historical multi-scale time sequence features of sample birds and corresponding historical egg production event occurrence marks; and based on the predicted egg production probability, it is determined whether an egg production event of the target bird occurs in the current monitoring period.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method, device, equipment, medium, and product for monitoring egg production. Background Technology

[0002] In the large-scale farming of poultry such as chickens, ducks, and geese, egg production is a key indicator for measuring economic benefits and population quality. To achieve digital and refined production management, accurate monitoring of the egg-laying behavior of each bird is necessary. Traditional monitoring methods relying on manual recording are inefficient and have a high error rate; therefore, a new egg production monitoring solution is needed to improve the efficiency and accuracy of egg production monitoring. Summary of the Invention

[0003] This application provides a method, apparatus, equipment, medium, and product for monitoring poultry egg production, which can improve the efficiency and accuracy of egg production monitoring.

[0004] In a first aspect, embodiments of this application provide a method for monitoring egg production, the method comprising: Obtain the RFID time sequence of the target poultry in the current monitoring period. The RFID time sequence includes the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. The monitoring values ​​indicate whether the RFID reader set in the egg-laying area reads the RFID tag set on the target poultry at the corresponding monitoring time point. Multi-scale time-series features are extracted from the RFID time-series sequence, and the multi-scale time-series features are input into the egg-laying probability prediction model to predict the egg-laying probability, thereby obtaining the predicted egg-laying probability; wherein, the egg-laying probability prediction model is trained based on the historical multi-scale time-series features of the sample poultry and the corresponding historical egg-laying event occurrence markers. Based on the predicted egg-laying probability, it is determined whether the target poultry will produce an egg-laying event during the current monitoring period.

[0005] In one embodiment, the monitoring time points are equally spaced time points, and the extraction of multi-scale temporal features from the RFID time series includes: The RFID time sequence is slid across multiple time windows of different lengths. For each time window, at each sliding position, a specified statistic of the local subsequence within the time window is calculated. The specified statistics calculated at each sliding position are concatenated to obtain the temporal characteristics of the scale corresponding to the time window. The specified statistics include: the number of times the RFID tag is read, the average time interval between reading the RFID tag, and the variance of the time interval between reading the RFID tag. The temporal features corresponding to each time window are spliced ​​together to generate the multi-scale temporal features.

[0006] In one embodiment, before inputting the multi-scale time-series features into the egg-laying probability prediction model to predict the egg-laying probability, the method further includes: Obtain a training dataset for predicting egg production probability. The training dataset includes: historical multi-scale time-series features of sample poultry and corresponding historical egg production event markers. The GBDT model is trained based on the training dataset to obtain the egg production probability prediction model.

[0007] In one embodiment, before obtaining the RFID time sequence of the target poultry in the current monitoring period, the method further includes: The RFID reader acquires reading data at each monitoring time point in the current monitoring cycle. The reading data includes: the monitoring time point and the tag ID of the read RFID tag. Each reading data contains the tag ID of an RFID tag. Each RFID tag is set on a poultry and is used to identify a poultry. Group the read data containing the same tag ID into a group to obtain the read data group corresponding to each tag ID in the current monitoring period; Based on the read data group corresponding to each tag ID in the current monitoring period, generate the RFID time sequence corresponding to each tag ID in the current monitoring period; Based on the RFID time sequence corresponding to each tag ID in the current monitoring period, generate a time sequence set for the current monitoring period; The acquisition of the RFID time sequence of the target poultry in the current monitoring period includes: Based on the tag ID of the RFID tag set on the target poultry, the RFID time sequence corresponding to the tag ID is obtained from the time sequence set of the current monitoring period.

[0008] In one embodiment, the method further includes: Each monitoring period of the current statistical period is taken as the current monitoring period in turn, and it is determined whether the target poultry has an egg-laying event in each monitoring period of the current statistical period. Based on whether the target poultry have an egg-laying event in each monitoring period of the current statistical period, calculate the egg-laying frequency of the target poultry in the current statistical period. If the egg-laying frequency of the target poultry in the current statistical period is less than the egg-laying frequency threshold of the current statistical period, then it is determined that the target poultry is laying eggs abnormally in the current statistical period. If the target poultry has abnormal egg production for N consecutive statistical periods, then the target poultry is identified as a suspected low-producing poultry.

[0009] In one embodiment, the egg-laying frequency threshold for the current statistical period is determined based on the average and variance of the egg-laying frequency of each poultry in the current statistical period.

[0010] Secondly, embodiments of this application provide an egg production monitoring device, the device comprising: The acquisition module is used to acquire the RFID time sequence of the target poultry in the current monitoring period. The RFID time sequence includes the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. The monitoring values ​​indicate whether the RFID reader set in the egg-laying area reads the RFID tag set on the target poultry at the corresponding monitoring time point. The prediction module is used to extract multi-scale time-series features from the RFID time-series sequence, input the multi-scale time-series features into the egg-laying probability prediction model to predict the egg-laying probability, and obtain the predicted egg-laying probability; wherein, the egg-laying probability prediction model is trained based on the historical multi-scale time-series features of the sample poultry and the corresponding historical egg-laying event occurrence markers; The determination module is used to determine, based on the predicted egg-laying probability, whether the target poultry has an egg-laying event in the current monitoring period.

[0011] Thirdly, embodiments of this application provide an electronic device, including: A memory on which computer programs are stored; A processor is used to execute the computer program to implement the above-described egg production monitoring method.

[0012] Fourthly, embodiments of this application provide a readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the above-described egg production monitoring method.

[0013] Fifthly, embodiments of this application provide a computer program product, including a computer program that can be executed by a processor to implement the above-described egg production monitoring method.

[0014] The technical solution provided in this application embodiment includes the RFID time-series sequence of the target poultry in the current monitoring period, which includes the monitoring values ​​corresponding to each monitoring time point within the current monitoring period. These monitoring values ​​indicate whether the RFID reader / writer set up in the egg-laying area read the RFID tag set on the target poultry at the corresponding monitoring time point. This represents the behavioral sequence of the target poultry in the egg-laying area at each monitoring time point within the current monitoring period, reflecting the poultry's loitering patterns in the egg-laying area. By acquiring the RFID time-series sequence of the target poultry in the current monitoring period, extracting multi-scale time-series features from this sequence, and inputting these features into an egg-laying probability prediction model to predict the egg-laying probability, the system determines whether an egg-laying event has occurred based on the predicted egg-laying probability. This allows for accurate prediction of the target poultry's egg-laying probability based on the multi-scale features of the behavioral sequence of whether the target poultry is in the egg-laying area at each monitoring time point within the current monitoring period, thereby improving the accuracy and efficiency of egg-laying monitoring. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the implementation environment to which the egg production monitoring method provided in this application embodiment is applicable; Figure 2 This is a schematic flowchart of an egg production monitoring method provided in an embodiment of this application; Figure 3 This is a schematic diagram of an RFID time sequence acquisition process provided in an embodiment of this application; Figure 4 This is a schematic diagram of the process for determining low-yielding suspected poultry, provided in an embodiment of this application. Figure 5 This is a schematic diagram of the structure of an egg production monitoring device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] This application provides an egg production monitoring method, apparatus, equipment, medium, and product.

[0018] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0019] The technical terms used in the embodiments of this application are explained as follows: RFID, Radio Frequency Identification.

[0020] GBDT, Gradient Boosting Decision Tree. Figure 1 This is a schematic diagram illustrating the implementation environment to which the egg production monitoring method provided in this application is applicable. For example... Figure 1 As shown, the implementation environment includes RFID tags, RFID readers, and a cloud service platform. RFID tags are attached to poultry such as chickens, ducks, and geese in poultry farms, with each tag uniquely identifying the bird. RFID readers are installed in the egg-laying area of ​​the farm to monitor whether poultry are in the egg-laying area. The reading range of the RFID reader is configured based on the area of ​​the egg-laying area, and its reading range is approximately equal to the area of ​​the egg-laying area. It is used to read RFID tags present in the egg-laying area. If the RFID reader reads an RFID tag, it means that the poultry identified by that RFID tag is in the egg-laying area; if the RFID reader does not read an RFID tag, it means that the poultry identified by that RFID tag is not in the egg-laying area.

[0021] The RFID reader is configured to continuously monitor the behavior of poultry over N monitoring cycles. Each monitoring cycle has multiple monitoring time points, which can be at equal intervals. At each monitoring time point within each monitoring cycle, the RFID reader can actively read RFID tags within its reading range and upload the read data to a cloud service platform. The read data includes the monitoring time point and the tag ID of the RFID tag read at the corresponding monitoring time point.

[0022] The cloud service platform can receive and store the read data uploaded by RFID readers. For each monitoring period, the cloud service platform can generate an RFID time sequence corresponding to each tag ID within that monitoring period based on the read data. Based on the RFID time sequence corresponding to each tag ID within that monitoring period, the platform can predict the probability of an egg-laying event occurring for each tag ID within that monitoring period. Based on this probability, the platform can determine whether an egg-laying event has occurred for the corresponding poultry within that monitoring period.

[0023] Each RFID time-series sequence corresponds to a tag ID, including the monitoring values ​​for each monitoring time point within the monitoring period. These monitoring values ​​indicate whether the RFID reader in the egg-laying area read the RFID tag of the poultry at the corresponding monitoring time point. The RFID time-series sequence is a behavioral sequence of whether the poultry identified by the tag ID was in the egg-laying area at each monitoring time point within the monitoring period. It reflects the poultry's access to and stay patterns in the egg-laying area. By predicting the probability of egg-laying events based on this RFID time-series sequence, and by accurately predicting the egg-laying probability of the corresponding poultry based on their continuous behavioral records in the egg-laying area, the accuracy of egg-laying event identification can be improved. Furthermore, the RFID time-series sequence is generated based on the data read by the RFID reader in the egg-laying area at the corresponding monitoring time points from the RFID tags on the poultry. This data collection scheme, which uses RFID readers to read RFID tags, is unaffected by environmental factors such as light and obstruction, resulting in high data accuracy and avoiding misjudgments of egg-laying events due to data collection errors. Furthermore, this solution only requires setting up RFID readers in the egg-laying area and attaching RFID tags to the poultry, making it easy to deploy and suitable for large-scale poultry flocks.

[0024] The egg production monitoring method provided in the embodiments of this application will be described in detail below.

[0025] Figure 2 This is a flowchart illustrating an egg production monitoring method provided in an embodiment of this application. This method can be executed by the aforementioned cloud service platform. Figure 2 As shown, the process includes: S202, Obtain the RFID time sequence of the target poultry in the current monitoring period.

[0026] The current monitoring period refers to the monitoring period for which analysis is currently being conducted, and it can be any monitoring period. The target poultry refers to the poultry to be analyzed, and it can be any poultry.

[0027] In implementation, the monitoring period can be configured based on the poultry's egg-laying cycle, which can be approximately equal to the egg-laying cycle. The egg-laying cycle can be the average time from the laying of one egg to the laying of the next. For example, if the poultry is a goose, which typically lays one egg per day, its egg-laying cycle is one day. Therefore, the monitoring period can be set to one day, and the current monitoring period can be the day from which the egg-laying event analysis is needed. By configuring the monitoring period based on the poultry's egg-laying cycle, the monitoring period can be matched with the poultry's egg-laying behavior patterns, avoiding misjudgments due to overly short observation periods or resource waste due to overly long observation periods.

[0028] The RFID time sequence of the target poultry in the current monitoring period is a continuous behavioral record of the target poultry during the current monitoring period, including the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. Monitoring time points can be at equal intervals. The monitoring value indicates whether the RFID reader / writer set up in the egg-laying area read the RFID tag set on the target poultry at the corresponding monitoring time point. For example, if the current monitoring period is... The monitoring time points within the current monitoring cycle can be... The monitoring value corresponding to each monitoring time point can be 0 or 1, where 0 indicates that the RFID tag set on the target poultry was not read at the corresponding monitoring time point. Of course, the monitoring time points can also be non-uniformly spaced. For example, the time interval between monitoring time points in the monitoring cycle can be non-uniform. The monitoring cycle can be divided into periods with a high probability of egg production and periods with a low probability of egg production. During periods with a high probability of egg production, the monitoring time point can be the first time interval, and during periods with a low probability of egg production, the monitoring time point can be the second time interval, where the first time interval is shorter than the second time interval.

[0029] In implementation, the reading range of the RFID reader can be configured based on the range of the egg-laying area, approximately equal to the range of the egg-laying area. If the RFID reader reads the RFID tag on the target poultry at the corresponding monitoring time point, it indicates that the target poultry is in the egg-laying area at that time point. If the RFID reader does not read the RFID tag on the target poultry at the corresponding monitoring time point, it indicates that the target poultry is not in the egg-laying area at that time point. The RFID time sequence of the target poultry within the current monitoring period is a behavioral sequence of whether the target poultry is in the egg-laying area at each monitoring time point within the current monitoring period. It can reflect information such as the target poultry's entry and exit time and dwell time in the egg-laying area. This information is related to whether the target poultry lays eggs within the current monitoring period and can be used to predict the probability of egg-laying events occurring in the current poultry within the current period.

[0030] S204. Extract multi-scale time-series features from RFID time-series sequences, input the multi-scale time-series features into the egg-laying probability prediction model to predict the egg-laying probability, and obtain the predicted egg-laying probability.

[0031] The egg production probability prediction model is used to predict egg production probability based on input multi-scale time-series features and output the predicted egg production probability. The predicted egg production probability is the actual egg production probability. This model can be trained based on the historical multi-scale time-series features of the sample poultry and corresponding historical egg production event markers. The historical multi-scale time-series features of the sample poultry are extracted from the RFID time-series sequences of the sample poultry within the historical monitoring period. The corresponding historical egg production event markers are used to identify whether an egg production event actually occurred for the sample poultry within that historical monitoring period.

[0032] In one embodiment, before inputting multi-scale temporal features into the egg production probability prediction model to predict egg production probability, a training dataset for egg production probability prediction can be obtained. The training dataset includes: historical multi-scale temporal features of sample poultry and corresponding historical egg production event markers; the GBDT model is trained based on the training dataset to obtain the egg production probability prediction model.

[0033] The GBDT model can be trained in a supervised manner by taking historical multi-scale time series features as input and the corresponding historical egg-laying time markers as output labels. The loss function used during training can be an appropriate loss function, such as the cross-entropy loss function.

[0034] The GBDT model can effectively handle nonlinear relationships and adapt to individual differences. By training the GBDT model based on historical multi-scale time series features and corresponding historical egg-laying event markers, the robustness of the egg-laying probability prediction model can be improved.

[0035] In the above embodiments, an egg production probability prediction model is trained based on historical multi-scale time-series features. Inputting these multi-scale time-series features into the model allows for comprehensive quantification of poultry behavior patterns across multiple time scales, improving the accuracy and robustness of egg production probability prediction. Multi-scale time-series features are used to describe poultry behavior patterns at different time scales and quantify poultry loitering patterns in egg-laying areas. In one embodiment, extracting multi-scale time-series features from an RFID time-series sequence includes: Slide multiple time windows of different durations across the RFID time sequence; For each time window, at each sliding position, a specified statistic of the local subsequence within that time window is calculated. The specified statistics calculated at each sliding position are then concatenated to obtain the temporal features of the scale corresponding to that time window. The temporal features corresponding to each time window are spliced ​​together to generate multi-scale temporal features.

[0036] Among them, multiple time windows with different time lengths are used to extract local subsequences from multiple time scales, and specified statistics are used to quantify local subsequences into modelable behavioral features.

[0037] Specified statistics may include: the number of times the RFID tags attached to the target poultry were read, the average time interval between reads, and the variance of the time interval. For example, in an RFID time series, 1 can represent that the RFID tag attached to the target poultry was read, and 0 can represent that the RFID tag attached to the target poultry was not read. The number of times 1 appears in a local subsequence can be counted, which is the number of times the RFID tag attached to the target poultry was read. The average time interval between adjacent 1 occurrences in a local subsequence can be counted, which is the average time interval between reads of the RFID tag attached to the target poultry. The variance of the average time interval between adjacent 1 occurrences in a local subsequence can be counted, which is the variance of the average time interval between reads of the RFID tag attached to the target poultry.

[0038] In one embodiment, to comprehensively reflect poultry behavior patterns, multiple time windows of varying lengths may include a first time window, a second time window, and a third time window. The first time window is shorter than the second time window, and the second time window is shorter than the third time window; that is, the first time window is a short-term window, the second time window is a medium-term window, and the third time window is a long-term window. The first time window is used to extract short-term subsequences from the RFID time series to quantify short-term behavior, for example, 5 minutes. The second time window is used to extract medium-term subsequences from the RFID time series to quantify medium-term behavior, for example, 1 hour. The third time window is used to extract long-term subsequences from the RFID time series to quantify long-term behavior, for example, 3 hours. A first time window can be used to slide across the RFID time series. At each sliding position, based on a local subsequence within the first time window, the number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval are calculated for that local subsequence. Then, the calculated number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval are concatenated to obtain the time series characteristics at the scale corresponding to the first time window, i.e., the short-term time series characteristics. A second time window can be used to slide across the RFID time series. At each sliding position, based on a local subsequence within the second time window, the number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval are calculated for that local subsequence. Then, the calculated number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval are concatenated to obtain the time series characteristics at the scale corresponding to the second time window, i.e., the medium-term time series characteristics. A third time window can be used to slide across the RFID time series. At each sliding position, based on the local subsequence within the third time window, the number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval are calculated for that local subsequence. Then, the number of times the RFID tags on the target poultry were read, the average time interval between reads, and the variance of the time interval calculated at each sliding position are concatenated to obtain the time series features corresponding to the scale of the third time window, i.e., the long-term time series features. Subsequently, the time series features corresponding to the scales of the first, second, and third time windows can be concatenated together to obtain multi-scale time series features.

[0039] S206, based on the predicted egg-laying probability, determines whether the target poultry will experience an egg-laying event during the current monitoring period.

[0040] Among them, the predicted egg production probability is the probability output by the egg production probability prediction model based on the RFID time series of the target poultry in the current monitoring period. It represents the probability that an egg production event will occur in the target poultry in the current monitoring period.

[0041] In one embodiment, the predicted egg-laying probability can be compared with a probability threshold. If the predicted egg-laying probability is greater than the probability threshold, it is determined that an egg-laying event has occurred in the target poultry during the current monitoring period, that is, the target poultry laid eggs during the current monitoring period. If the predicted egg-laying probability is not greater than the probability threshold, that is, less than or equal to the probability threshold, it is determined that no egg-laying event has occurred in the target poultry during the current monitoring period, that is, the target poultry did not lay eggs during the current monitoring period.

[0042] In this embodiment, the RFID time-series sequence of the target poultry in the current monitoring period includes the monitoring values ​​corresponding to each monitoring time point within the current monitoring period. These monitoring time points are equally spaced. Each monitoring value indicates whether the RFID reader located in the egg-laying area reads the RFID tag on the target poultry at the corresponding monitoring time point. It represents the behavioral sequence of whether the target poultry was in the egg-laying area at each monitoring time point in the current monitoring period. If the RFID reader reads the RFID tag on the target poultry at the corresponding monitoring time point, it indicates that the target poultry was in the egg-laying area at that time point. If the RFID reader does not read the RFID tag on the target poultry at the corresponding monitoring time point, it indicates that the target poultry was not in the egg-laying area at that time point. The multi-scale temporal features extracted from the RFID time-series sequence can comprehensively reflect the poultry's behavioral patterns. By acquiring the RFID time-series sequence of the target poultry within the current monitoring period, multi-scale time-series features are extracted from the RFID time-series sequence. These multi-scale time-series features are then input into the egg-laying probability prediction model to predict the egg-laying probability. Based on the predicted egg-laying probability, it is determined whether an egg-laying event has occurred. This method can accurately predict the egg-laying probability of the target poultry based on the multi-scale features of the behavioral sequence of whether the target poultry is in the egg-laying area at each monitoring time point in the current monitoring period, thereby improving the accuracy and efficiency of egg-laying monitoring.

[0043] In the above embodiment, in step S202, the RFID time sequence of the target poultry in the current monitoring period is obtained. The RFID time sequence of the target poultry in the current monitoring period can be generated based on the reading data of the RFID reader at each monitoring time point in the current monitoring period. Figure 3 This is a schematic diagram of an RFID time sequence acquisition process provided in an embodiment of this application, such as... Figure 3 As shown, before step S202, the procedure further includes: S302, acquire the reading data of the RFID reader at each monitoring time point in the current monitoring cycle.

[0044] The read data includes: the monitoring time point and the tag ID of the read RFID tag. Each read data contains the tag ID of an RFID tag. Each RFID tag is set on a poultry and is used to identify a poultry.

[0045] For example, reading data can be . To monitor time points, In order to be in The tag ID of an RFID tag that has been read.

[0046] S304. Group the read data containing the same tag ID into a group to obtain the read data group corresponding to each tag ID in the current monitoring period.

[0047] Each tag ID corresponds to a data group, and the data in each data group contains the same tag ID, which is its corresponding tag ID.

[0048] S306, based on the read data group corresponding to each tag ID in the current monitoring period, generates the RFID time sequence corresponding to each tag ID in the current monitoring period.

[0049] Specifically, for each tag ID corresponding to the read data group, the time points of each monitoring time point in the current monitoring cycle can be used as the time points of the time sequence. Based on the read data group corresponding to the tag ID, it can be determined whether the RFID tag identified by the tag ID was read at the monitoring time point. If yes, the monitoring value of the time point is set to 1; if no, the monitoring value of the time point is set to 0, thereby generating the RFID time sequence corresponding to the tag ID.

[0050] For example, for tag ID1, if the data to be read in the data group corresponding to tag ID1 is: Based on this data, the monitoring time point can be determined. , , Read The identified RFID tag was not read at other times. The identified RFID tags will monitor the time points. , , Each corresponding monitoring value is set to 1, and the monitoring values ​​corresponding to other monitoring time points in the current monitoring period are set to 0, thereby generating the current monitoring period. The corresponding RFID timing sequence.

[0051] S308, based on the RFID time sequence corresponding to each tag ID in the current monitoring period, generates a time sequence set for the current monitoring period.

[0052] The time sequence set for the current monitoring period includes the RFID time sequence corresponding to each tag ID in the current monitoring period.

[0053] In step S202, obtaining the RFID time sequence of the target poultry within the current monitoring period includes: Based on the tag ID of the RFID tag affixed to the target poultry, the RFID time sequence corresponding to that tag ID is obtained from the time sequence set of the current monitoring period. This RFID time sequence is the RFID time sequence of the target poultry in the current monitoring period.

[0054] In this embodiment, the reading data of the RFID reader at each monitoring time point in the current monitoring period is obtained. Based on the reading data of the RFID reader at each monitoring time point in the current monitoring period, an RFID time sequence set for the current monitoring period is generated. This facilitates the subsequent determination of whether each poultry has experienced an egg-laying event in the current monitoring period based on the RFID time sequence set for the current monitoring period.

[0055] In implementation, the RFID reader can continuously read RFID tags within its reading range at each monitoring time point of N monitoring cycles and upload the read data to the cloud service platform. The cloud service platform can execute steps S302 to S308 above for each monitoring cycle to obtain the RFID time sequence set for each monitoring cycle. Further, the cloud service platform can sequentially use each monitoring cycle as the current monitoring cycle and each poultry as the target poultry, executing steps S202 to S206 above to determine whether an egg-laying event has occurred for each poultry in each monitoring cycle. This method can be used for large-scale poultry flocks in farms, facilitating the precise determination of the egg-laying status of each poultry in a large flock.

[0056] In one embodiment, furthermore, low-producing birds can be identified based on whether any egg-laying events occurred in each bird during each monitoring period. For example... Figure 4 As shown in the embodiments of this application, the egg production monitoring method further includes the following steps: S402, sequentially taking each monitoring period of the current statistical period as the current monitoring period, determine whether the target poultry have experienced egg production events in each monitoring period of the current statistical period.

[0057] The current statistical period refers to the statistical period currently being analyzed. It can be any statistical period, and a statistical period can include multiple consecutive monitoring periods. For example, a monitoring period can be one day, and a statistical period can be one week. Each monitoring period of the current statistical period can be used as the current monitoring period, and the above steps S202~S206 can be executed sequentially to determine whether the target poultry have experienced an egg-laying event in each monitoring period of the current statistical period.

[0058] S404, Calculate the egg production frequency of the target poultry in the current statistical period based on whether the target poultry have egg production events in each monitoring period of the current statistical period.

[0059] S406, If the egg-laying frequency of the target poultry in the current statistical period is less than the egg-laying frequency threshold of the current statistical period, then it is determined that the egg-laying of the target poultry is abnormal in the current statistical period.

[0060] Among them, the egg production probability threshold for the current statistical period can be a dynamic threshold, which can change with the statistical period.

[0061] In one embodiment, the egg-laying probability threshold for the current statistical period can be determined based on the egg-laying frequency of each poultry in the current statistical period. For example, the average and variance of the egg-laying frequency of each poultry in the current statistical period can be calculated, and the egg-laying frequency threshold for the current statistical period can be determined based on the average and variance of the egg-laying frequency of each poultry in the current statistical period. The egg-laying frequency threshold can be:

[0062] in, This represents the average egg-laying frequency of each poultry species during the current statistical period. This represents the standard deviation of the egg-laying frequency of each poultry species during the current statistical period. This is the sensitivity coefficient, which can be configured to adjust the stringency of the recognition threshold.

[0063] In this embodiment, the egg production frequency threshold for the current statistical period is determined by the average value and variance of the egg production frequency of each poultry in the current statistical period. This provides a dynamic baseline for the egg production frequency and avoids misjudgment caused by overall physiological changes in the poultry flock.

[0064] S408. If the target poultry has abnormal egg production for N consecutive statistical periods, then the target poultry is identified as a suspected low-producing poultry.

[0065] in, N is a configurable value, such as 2, 3, etc.

[0066] In this embodiment, if a target bird exhibits abnormal egg production for N consecutive statistical periods, it is identified as a suspected low-producing bird. This approach combines egg production data from multiple statistical periods to more accurately identify suspected low-producing birds, avoiding misjudgments due to fluctuations in data from a single period. Furthermore, by determining an egg production frequency threshold for the current statistical period based on the egg production frequency of each bird, and comparing the target bird's egg production frequency with this threshold, it is determined whether the target bird exhibits abnormal egg production in the current statistical period. When the target bird exhibits abnormal egg production for N consecutive statistical periods, it is identified as a low-producing bird. This approach combines statistical bias and persistence to perform a dual judgment on whether a target bird is a suspected low-producing bird, improving the reliability of the judgment.

[0067] In practice, each bird in the poultry flock of the farm can be selected as the target bird in turn, and the above steps S402 to S408 can be executed to determine whether each bird is a suspected low-production bird and output a list of suspected low-production birds, thereby providing decision support for farm personnel and achieving a balance between intelligence and risk control.

[0068] The above are egg production monitoring methods provided in the embodiments of this application. Based on the same idea as the above embodiments, the embodiments of this application also provide an egg production monitoring device. Figure 5 As shown, the egg production monitoring device 500 includes: The acquisition module 510 is used to acquire the RFID time sequence of the target poultry in the current monitoring period. The RFID time sequence includes the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. The monitoring values ​​indicate whether the RFID reader set in the egg-laying area reads the RFID tag set on the target poultry at the corresponding monitoring time point. The prediction module 520 is used to extract multi-scale time-series features from the RFID time-series sequence, input the multi-scale time-series features into the egg-laying probability prediction model to predict the egg-laying probability, and obtain the predicted egg-laying probability; wherein, the egg-laying probability prediction model is trained based on the historical multi-scale time-series features of the sample poultry and the corresponding historical egg-laying event occurrence markers. The determination module 530 is used to determine, based on the predicted egg-laying probability, whether the poultry has experienced an egg-laying event in the current monitoring period.

[0069] In one embodiment, the prediction module 520 is specifically used for: The RFID time sequence is slid across multiple time windows of different lengths. For each time window, at each sliding position, a specified statistic of the local subsequence within the time window is calculated. The specified statistics calculated at each sliding position are concatenated to obtain the temporal characteristics of the scale corresponding to the time window. The specified statistics include: the number of times the RFID tag is read, the average time interval between reading the RFID tag, and the variance of the time interval between reading the RFID tag. The temporal features corresponding to each time window are spliced ​​together to generate the multi-scale temporal features.

[0070] In one embodiment, the egg production monitoring device further includes a training module for: Obtain a training dataset for predicting egg production probability. The training dataset includes: historical multi-scale time-series features of sample poultry and corresponding historical egg production event markers. The GBDT model is trained based on the training dataset to obtain the egg production probability prediction model.

[0071] In one embodiment, the egg-laying monitoring device 500 further includes: a dataset generation module, used for: The RFID reader acquires reading data at each monitoring time point in the current monitoring cycle. The reading data includes: the monitoring time point and the tag ID of the read RFID tag. Each reading data contains the tag ID of an RFID tag. Each RFID tag is set on a poultry and is used to identify a poultry. Group the read data containing the same tag ID into a group to obtain the read data group corresponding to each tag ID in the current monitoring period; Based on the read data group corresponding to each tag ID in the current monitoring period, generate the RFID time sequence corresponding to each tag ID in the current monitoring period; Based on the RFID time sequence corresponding to each tag ID in the current monitoring period, generate a time sequence set for the current monitoring period; The acquisition module 410 is specifically used for: Based on the tag ID of the RFID tag set on the target poultry, the RFID time sequence corresponding to the tag ID is obtained from the time sequence set of the current monitoring period.

[0072] In one embodiment, the egg production monitoring device 500 further includes: a low-production analysis module, used for: Each monitoring period of the current statistical period is taken as the current monitoring period in turn, and it is determined whether the target poultry has an egg-laying event in each monitoring period of the current statistical period. Based on whether the target poultry have an egg-laying event in each monitoring period of the current statistical period, calculate the egg-laying frequency of the target poultry in the current statistical period. If the egg-laying frequency of the target poultry in the current statistical period is less than the egg-laying frequency threshold of the current statistical period, then it is determined that the target poultry is laying eggs abnormally in the current statistical period. If the target poultry has abnormal egg production for N consecutive statistical periods, then the target poultry is identified as a suspected low-producing poultry.

[0073] In one embodiment, the egg-laying frequency threshold for the current statistical period is determined based on the average and variance of the egg-laying frequency of each poultry in the current statistical period.

[0074] The egg production monitoring device in this application embodiment can serve as the execution subject of the above-mentioned egg production monitoring method, realizing all the functions of the above-mentioned egg production monitoring method. Since the principle is the same, it will not be described again here.

[0075] Based on the same ideas as the above embodiments, this application also provides an electronic device. For example... Figure 6 As shown, the electronic device 600 can vary considerably due to differences in configuration or performance, and may include one or more memories 610 and processors 620. The memory 610 stores a computer program, and the processor 620 processes the computer program to implement the aforementioned egg production monitoring method. To avoid repetition, further details are omitted here.

[0076] Furthermore, one or more embodiments of this application also provide a non-transient readable storage medium for storing a computer program. In one specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc. The computer program stored on the storage medium can be executed by a processor to implement the above-described egg production monitoring method. To avoid repetition, further details will not be provided here.

[0077] Furthermore, one or more embodiments of this application also provide a computer program product, including a computer program that can be executed by a processor to implement the above-described egg production monitoring method. To avoid repetition, further details are omitted here.

[0078] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the operator programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0080] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0081] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0082] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0083] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this application may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] Embodiments of this application are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable parallel device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable parallel device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable fraud device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0089] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the text "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this application may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this application may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] One or more embodiments of this application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. One or more embodiments of this application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0093] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0095] It should be understood that the training and prediction processes of the AI ​​models involved in the various embodiments of this application all adhere to the principles of legal data sources, compliant data content, and compliant data governance, and comply with the requirements of Article 5 of the Patent Law. Specifically: Data source legitimacy: All datasets used for AI model training were obtained through legal means, covering three categories: publicly authorized data, data authorized by partners, and self-collected compliant data. Publicly authorized data comes from compliant data sources following open-source licenses such as Apache 2.0, with complete copyright attribution and authorization scope clearly marked, and no unauthorized open-source code or data reuse. Data authorized by partners has been subject to formal data usage agreements, clearly defining the scope, duration, and confidentiality obligations, and possessing a complete authorization chain. For self-collected data involving personal information, strict informed consent procedures have been followed, and anonymization processes (including but not limited to field masking, feature anonymization, and differential privacy technology applications) have been implemented to remove personally identifiable information, fully complying with the requirements of relevant laws and regulations such as the "Interim Measures for the Administration of Generative Artificial Intelligence Services" and the "Personal Information Protection Law."

[0096] Data content compliance: The AI ​​model's dataset undergoes multiple screenings and cleaning processes to remove all content that may violate social morality or harm public interests. It contains no obscene, pornographic, violent, discriminatory, or information that endangers national or public safety, nor does it involve the illegal acquisition or use of genetic resources. For data in sensitive fields (such as healthcare and finance), an additional privacy-preserving computation module (including federated learning and secure multi-party computation technologies) ensures that the data is "usable but not visible," avoiding compliance risks during the original data transmission process and ensuring that the data application scenarios and uses comply with public order and good morals and industry regulatory requirements.

[0097] Data governance norms: A complete data traceability system is established during the AI ​​model training process to automatically record the source, collection time, annotation process, cleaning rules, and permission allocation of training data, generating traceable compliance reports to ensure that the data is verifiable throughout its entire lifecycle. The dataset annotation process for AI models is completed by a professional human R&D team, clearly defining the proportion of human creative contributions and avoiding reliance on AI-generated data that has not undergone substantial human modification, thus meeting the examination requirements for "human main contributions" in AI patent applications.

Claims

1. A method for monitoring egg production, characterized in that, The method includes: Obtain the RFID time sequence of the target poultry in the current monitoring period. The RFID time sequence includes the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. The monitoring values ​​indicate whether the RFID reader set in the egg-laying area reads the RFID tag set on the target poultry at the corresponding monitoring time point. Multi-scale time-series features are extracted from the RFID time-series sequence, and the multi-scale time-series features are input into the egg-laying probability prediction model to predict the egg-laying probability, thereby obtaining the predicted egg-laying probability; wherein, the egg-laying probability prediction model is trained based on the historical multi-scale time-series features of the sample poultry and the corresponding historical egg-laying event occurrence markers. Based on the predicted egg-laying probability, it is determined whether the target poultry will produce an egg-laying event during the current monitoring period.

2. The method according to claim 1, characterized in that, The monitoring time points are at equal intervals, and the extraction of multi-scale temporal features from the RFID time series includes: The RFID time sequence is slid across multiple time windows of different lengths. For each time window, at each sliding position, a specified statistic of the local subsequence within the time window is calculated. The specified statistics calculated at each sliding position are concatenated to obtain the temporal characteristics of the scale corresponding to the time window. The specified statistics include: the number of times the RFID tag is read, the average time interval between reading the RFID tag, and the variance of the time interval between reading the RFID tag. The temporal features corresponding to each time window are spliced ​​together to generate the multi-scale temporal features.

3. The method according to claim 1, characterized in that, Before inputting the multi-scale time-series features into the egg production probability prediction model to predict the egg production probability, the method further includes: Obtain a training dataset for predicting egg production probability. The training dataset includes: historical multi-scale time-series features of sample poultry and corresponding historical egg production event markers. The GBDT model is trained based on the training dataset to obtain the egg production probability prediction model.

4. The method according to claim 1, characterized in that, Before obtaining the RFID time sequence of the target poultry in the current monitoring period, the method further includes: The RFID reader acquires reading data at each monitoring time point in the current monitoring cycle. The reading data includes: the monitoring time point and the tag ID of the read RFID tag. Each reading data contains the tag ID of an RFID tag. Each RFID tag is set on a poultry and is used to identify a poultry. Group the read data containing the same tag ID into a group to obtain the read data group corresponding to each tag ID in the current monitoring period; Based on the read data group corresponding to each tag ID in the current monitoring period, generate the RFID time sequence corresponding to each tag ID in the current monitoring period; Based on the RFID time sequence corresponding to each tag ID in the current monitoring period, generate a time sequence set for the current monitoring period; The acquisition of the RFID time sequence of the target poultry in the current monitoring period includes: Based on the tag ID of the RFID tag set on the target poultry, the RFID time sequence corresponding to the tag ID is obtained from the time sequence set of the current monitoring period.

5. The method according to claim 1, characterized in that, The method further includes: Each monitoring period of the current statistical period is taken as the current monitoring period in turn, and it is determined whether the target poultry has an egg-laying event in each monitoring period of the current statistical period. Based on whether the target poultry have an egg-laying event in each monitoring period of the current statistical period, calculate the egg-laying frequency of the target poultry in the current statistical period. If the egg-laying frequency of the target poultry in the current statistical period is less than the egg-laying frequency threshold of the current statistical period, then it is determined that the target poultry is laying eggs abnormally in the current statistical period. If the target poultry has abnormal egg production for N consecutive statistical periods, then the target poultry is identified as a suspected low-producing poultry.

6. The method according to claim 5, characterized in that, The egg production frequency threshold for the current statistical period is determined based on the average and variance of the egg production frequency of each poultry in the current statistical period.

7. An egg production monitoring device, characterized in that, The device includes: The acquisition module is used to acquire the RFID time sequence of the target poultry in the current monitoring period. The RFID time sequence includes the monitoring values ​​corresponding to each monitoring time point in the current monitoring period. The monitoring values ​​indicate whether the RFID reader set in the egg-laying area reads the RFID tag set on the target poultry at the corresponding monitoring time point. The prediction module is used to extract multi-scale time-series features from the RFID time-series sequence, input the multi-scale time-series features into the egg-laying probability prediction model to predict the egg-laying probability, and obtain the predicted egg-laying probability; wherein, the egg-laying probability prediction model is trained based on the historical multi-scale time-series features of the sample poultry and the corresponding historical egg-laying event occurrence markers; The determination module is used to determine, based on the predicted egg-laying probability, whether the target poultry has an egg-laying event in the current monitoring period.

8. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program to implement the egg production monitoring method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the egg production monitoring method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that can be executed by a processor to implement the egg production monitoring method according to any one of claims 1 to 6.

Images